aiqbench analysis
This preprint details a practical framework for federated learning that addresses data privacy constraints by enabling collaborative model training across decentralized devices like smartphones and sensors. The authors propose a mathematically principled approach using generalized total variation minimization to personalize models based on device similarity within a network graph, bridging the gap between optimization theory and real-world deployment.
Federated Learning: From Theory to Practice
arXiv:2505.19183v3 Announce Type: replace Abstract: This book offers a hands-on introduction to building and understanding federated learning (FL) systems. FL enables multiple devices -- such as smartphones, sensors, or local computers -- to collaboratively train machine learning (ML) models, while keeping their data private and local. It is a powerful solution when data cannot or should not be centralized due to privacy, regulatory, or technical reasons. The book is designed for students, engineers, and researchers who want to learn how to design scalable, privacy preserving FL systems. Our main focus is on personalization: enabling each device to train its own model while still benefiting from collaboration with relevant devices. This is achieved by leveraging similarities between (the learning tasks associated with) devices that are encoded by the weighted edges (or links) of a federated learning network (FL network). The key idea is to represent real-world FL systems as networks of devices, where nodes correspond to device and edges represent communication links and data similarities between them. The training of personalized models for these devices can be naturally framed as a distributed optimization problem. This optimization problem is referred to as generalized total variation minimization (GTVMin) and ensures that devices with similar learning tasks learn similar model parameters. Our approach is both mathematically principled and practically motivated. While we introduce some advanced ideas from optimization theory and graph-based learning, we aim to keep the book accessible. Readers are guided through the core ideas step by step, with intuitive explanations.
arXiv:2505.19183 (cs)
Abstract:This book offers a hands-on introduction to building and understanding federated learning (FL) systems. FL enables multiple devices -- such as smartphones, sensors, or local computers -- to collaboratively train machine learning (ML) models, while keeping their data private and local. It is a powerful solution when data cannot or should not be centralized due to privacy, regulatory, or technical reasons. The book is designed for students, engineers, and researchers who want to learn how to design scalable, privacy preserving FL systems. Our main focus is on personalization: enabling each device to train its own model while still benefiting from collaboration with relevant devices. This is achieved by leveraging similarities between (the learning tasks associated with) devices that are encoded by the weighted edges (or links) of a federated learning network (FL network). The key idea is to represent real-world FL systems as networks of devices, where nodes correspond to device and edges represent communication links and data similarities between them. The training of personalized models for these devices can be naturally framed as a distributed optimization problem. This optimization problem is referred to as generalized total variation minimization (GTVMin) and ensures that devices with similar learning tasks learn similar model parameters. Our approach is both mathematically principled and practically motivated. While we introduce some advanced ideas from optimization theory and graph-based learning, we aim to keep the book accessible. Readers are guided through the core ideas step by step, with intuitive explanations.
252 pages. This is a preprint of the following work: A. Jung, Federated Learning: From Theory to Practice, 2026, Springer, reproduced with permission of Springer Nature Singapore Pte Ltd. The final authenticated version is available online at: this https URL
Machine Learning (cs.LG); Machine Learning (stat.ML)
F.1.1; I.2.11; I.5.3
arXiv:2505.19183 [cs.LG]
(or arXiv:2505.19183v3 [cs.LG] for this version)
Springer Nature Singapore, 2026. ISBN 978-981-95-1008-5
https://doi.org/10.1007/978-981-95-1009-2 DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 386 words
Related coverage
StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participation
arXiv · Oct 2, 2026
FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning
arXiv · Oct 15, 2026
Federated Learning for Distributed CNC Tool Wear Prediction
arXiv · Sep 22, 2026
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning
arXiv · Jun 10, 2026